Implementation Speech Recognition for Robot Control Using MFCC and ANFIS

Trima Mustofa


Speech recognition is one of machine intelligence field that grow rapidly, it is recognized by almost all technology devices that equipped by voice command. The process of converting voice patterns into text through complex transcription process. There is an enormous complexity involved in analyzing speech input, such as variations in pronunciation, accent, speaker physiology, emphasis and acoustic environmental characteristics in generating hundreds of different phoneme classifications for each sound. A sound pattern recognition system is required to process sound signals quickly and realtime in recognizing voice input with accurate results. In this case MFCC is an appropriate method to apply sound extraction because it presents the signal well. While ANFIS is needed for sound characteristic learning because it has advantages possessed by fuzzy inference system and artificial neural network system. In this research tested through robot control.

Keywords: ANFIS, MFCC, Speech Recognition, Robot Control

Full Text: PDF


  • There are currently no refbacks.

View JTI Stats